2020
DOI: 10.1016/j.conbuildmat.2020.118271
|View full text |Cite
|
Sign up to set email alerts
|

An ensemble machine learning approach for prediction and optimization of modulus of elasticity of recycled aggregate concrete

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

3
66
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 159 publications
(69 citation statements)
references
References 64 publications
3
66
0
Order By: Relevance
“…This could be explained by its being an ensemble algorithm. The findings are in corroboration with Han et al [9] who assert that ensemble algorithms tend to perform better than stand-alone algorithms. However, GBM and XGB gave lower accuracy than the DT classifier unlike expectation.…”
Section: Resultssupporting
confidence: 88%
“…This could be explained by its being an ensemble algorithm. The findings are in corroboration with Han et al [9] who assert that ensemble algorithms tend to perform better than stand-alone algorithms. However, GBM and XGB gave lower accuracy than the DT classifier unlike expectation.…”
Section: Resultssupporting
confidence: 88%
“…As a distinct indicator for evaluating the performance of a machine learning model, R (Pearson’s correlation coefficient) or R 2 (coefficient of determination) are useful. Thus, many researchers (e.g., Qi et al (2018) [ 44 ]; Han et al (2020) [ 45 ]; Kannangara et al (2018) [ 27 ]; Kumar et al (2018) [ 21 ]) used the R or R 2 value between the observed and predicted value for assessing the performance of prediction models. In this study, for performance evaluation of the prediction model, the R (correlation coefficient) value, which is given by Equations (3) and (4), between the observed and predicted values was used as the performance indicator.…”
Section: Development Of a Dw Prediction Modelmentioning
confidence: 99%
“…The proficiency of the RF model’s in terms of promptly producing high-fidelity predictions of cement hydration kinetics (in the forms of time-dependent cumulative heat release and heat flow rate) is anticipated, given the large body of published research 54 – 56 , 58 , 59 , 73 , 77 , 91 ; in which it has consistently been shown that the RF model—and other decision trees-based models—generally outperform other models that are based on nonlinear regression analyses (e.g., elastic net regression), or an assortment of logistic transfer functions (e.g., artificial neural networks), or data clustering/mapping mechanisms (e.g., support vector machines). To benchmark the prediction performance of the RF model, two additional ML models developed and used in our previous studies 55 , 57 – 59 , 92 —the multilayer perceptron artificial neural network (MLP-ANN) model; and support vector machine (SVM)—were used to produce predictions of heat release behavior, and compared against those produced by the RF model (see Fig.…”
Section: Resultsmentioning
confidence: 99%
“…The random forests (RF) model—based on an ensemble of 100–1000 s of uncorrelated classification-and-regression-trees (CART) 55 , 58 , 59 , 73 —is used in this study. The RF model is premised on: (1) Building uncorrelated decision trees (i.e., CARTs) at a large scale; (2) Grouping CARTs into committees, so as to produce independent outputs; and (3) Averaging outputs produced by all CARTs to estimate the final output 74 .…”
Section: Overview Of the Random Forests Modelmentioning
confidence: 99%
See 1 more Smart Citation